Automated Industry Classification of Chinese Enterprises Based on Business Scope Texts Using Deep Learning Methods

Jun Liu; Lu Bai; Zhibao Wang; Haochang Wang; Man Zhao; Chengbo Wang

doi:10.1109/issc59246.2023.10162035

Automated Industry Classification of Chinese Enterprises Based on Business Scope Texts Using Deep Learning Methods

Jun Liu, Lu Bai, Zhibao Wang, Haochang Wang, Man Zhao, Chengbo Wang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The rapid development of China’s economy has led to a significant increase in the number of enterprises. Industry classification of enterprises based on their business scope text can help analyse industry development and enable efficient management of enterprise information. In this paper, we employ deep learning methods to classify Chinese enterprises by industry using business scope texts. To automate the classification process, we first pre-process business scope texts data based on their characteristics. We then construct several deep learning models including TextCNN, TextRCNN, TextRNN_Att and fastText to classify Chinese enterprises based on their business scope texts. The TextCNN model achieved the best text classification performance with an accuracy of 95.67%. Our experimental results demonstrate that the proposed approach is effective in classifying Chinese enterprises by industry based on their business scope texts.

Original language	English
Title of host publication	Proceedings of 2023 34th Irish Signals and Systems Conference (ISSC)
Publisher	IEEE
Pages	1-6
Number of pages	6
ISBN (Electronic)	979-8-3503-4057-0
ISBN (Print)	979-8-3503-4058-7
DOIs	https://doi.org/10.1109/issc59246.2023.10162035
Publication status	Published online - 3 Jul 2023
Event	34th Irish Signals and Systems Conference (ISSC 2023) - University College Dublin, Dublin, Ireland Duration: 13 Jun 2023 → 14 Jun 2023 https://issc.ie/index.html

Publication series

Name	2023 34th Irish Signals and Systems Conference (ISSC)
Publisher	IEEE Control Society

Conference

Conference	34th Irish Signals and Systems Conference (ISSC 2023)
Abbreviated title	ISSC 2023
Country/Territory	Ireland
City	Dublin
Period	13/06/23 → 14/06/23
Internet address	https://issc.ie/index.html

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

TextCNN
TextRCNN
TextRNN_Att
fastText
Classification of enterprises
Industries
Deep learning
Training
Analytical models
Biological system modelling
Text categorization
Carbon dioxide

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/issc59246.2023.10162035

Cite this

Liu, J., Bai, L., Wang, Z., Wang, H., Zhao, M., & Wang, C. (2023). Automated Industry Classification of Chinese Enterprises Based on Business Scope Texts Using Deep Learning Methods. In Proceedings of 2023 34th Irish Signals and Systems Conference (ISSC) (pp. 1-6). (2023 34th Irish Signals and Systems Conference (ISSC)). IEEE. Advance online publication. https://doi.org/10.1109/issc59246.2023.10162035

@inproceedings{7825b35bb01949b1bf37b07a4c86d1a3,

title = "Automated Industry Classification of Chinese Enterprises Based on Business Scope Texts Using Deep Learning Methods",

abstract = "The rapid development of China{\textquoteright}s economy has led to a significant increase in the number of enterprises. Industry classification of enterprises based on their business scope text can help analyse industry development and enable efficient management of enterprise information. In this paper, we employ deep learning methods to classify Chinese enterprises by industry using business scope texts. To automate the classification process, we first pre-process business scope texts data based on their characteristics. We then construct several deep learning models including TextCNN, TextRCNN, TextRNN_Att and fastText to classify Chinese enterprises based on their business scope texts. The TextCNN model achieved the best text classification performance with an accuracy of 95.67%. Our experimental results demonstrate that the proposed approach is effective in classifying Chinese enterprises by industry based on their business scope texts.",

keywords = "TextCNN, TextRCNN, TextRNN_Att, fastText, Classification of enterprises, Industries, Deep learning, Training, Analytical models, Biological system modelling, Text categorization, Carbon dioxide",

author = "Jun Liu and Lu Bai and Zhibao Wang and Haochang Wang and Man Zhao and Chengbo Wang",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 34th Irish Signals and Systems Conference (ISSC 2023), ISSC 2023 ; Conference date: 13-06-2023 Through 14-06-2023",

year = "2023",

month = jul,

day = "3",

doi = "10.1109/issc59246.2023.10162035",

language = "English",

isbn = "979-8-3503-4058-7",

series = "2023 34th Irish Signals and Systems Conference (ISSC)",

publisher = "IEEE",

pages = "1--6",

booktitle = "Proceedings of 2023 34th Irish Signals and Systems Conference (ISSC)",

address = "United States",

url = "https://issc.ie/index.html",

}

Liu, J, Bai, L, Wang, Z, Wang, H, Zhao, M & Wang, C 2023, Automated Industry Classification of Chinese Enterprises Based on Business Scope Texts Using Deep Learning Methods. in Proceedings of 2023 34th Irish Signals and Systems Conference (ISSC). 2023 34th Irish Signals and Systems Conference (ISSC), IEEE, pp. 1-6, 34th Irish Signals and Systems Conference (ISSC 2023), Dublin, Ireland, 13/06/23. https://doi.org/10.1109/issc59246.2023.10162035

Automated Industry Classification of Chinese Enterprises Based on Business Scope Texts Using Deep Learning Methods. / Liu, Jun; Bai, Lu; Wang, Zhibao et al.
Proceedings of 2023 34th Irish Signals and Systems Conference (ISSC). IEEE, 2023. p. 1-6 (2023 34th Irish Signals and Systems Conference (ISSC)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Automated Industry Classification of Chinese Enterprises Based on Business Scope Texts Using Deep Learning Methods

AU - Liu, Jun

AU - Bai, Lu

AU - Wang, Zhibao

AU - Wang, Haochang

AU - Zhao, Man

AU - Wang, Chengbo

PY - 2023/7/3

Y1 - 2023/7/3

N2 - The rapid development of China’s economy has led to a significant increase in the number of enterprises. Industry classification of enterprises based on their business scope text can help analyse industry development and enable efficient management of enterprise information. In this paper, we employ deep learning methods to classify Chinese enterprises by industry using business scope texts. To automate the classification process, we first pre-process business scope texts data based on their characteristics. We then construct several deep learning models including TextCNN, TextRCNN, TextRNN_Att and fastText to classify Chinese enterprises based on their business scope texts. The TextCNN model achieved the best text classification performance with an accuracy of 95.67%. Our experimental results demonstrate that the proposed approach is effective in classifying Chinese enterprises by industry based on their business scope texts.

AB - The rapid development of China’s economy has led to a significant increase in the number of enterprises. Industry classification of enterprises based on their business scope text can help analyse industry development and enable efficient management of enterprise information. In this paper, we employ deep learning methods to classify Chinese enterprises by industry using business scope texts. To automate the classification process, we first pre-process business scope texts data based on their characteristics. We then construct several deep learning models including TextCNN, TextRCNN, TextRNN_Att and fastText to classify Chinese enterprises based on their business scope texts. The TextCNN model achieved the best text classification performance with an accuracy of 95.67%. Our experimental results demonstrate that the proposed approach is effective in classifying Chinese enterprises by industry based on their business scope texts.

KW - TextCNN

KW - TextRCNN

KW - TextRNN_Att

KW - fastText

KW - Classification of enterprises

KW - Industries

KW - Deep learning

KW - Training

KW - Analytical models

KW - Biological system modelling

KW - Text categorization

KW - Carbon dioxide

UR - http://www.scopus.com/inward/record.url?scp=85166000417&partnerID=8YFLogxK

U2 - 10.1109/issc59246.2023.10162035

DO - 10.1109/issc59246.2023.10162035

M3 - Conference contribution

SN - 979-8-3503-4058-7

T3 - 2023 34th Irish Signals and Systems Conference (ISSC)

SP - 1

EP - 6

BT - Proceedings of 2023 34th Irish Signals and Systems Conference (ISSC)

PB - IEEE

T2 - 34th Irish Signals and Systems Conference (ISSC 2023)

Y2 - 13 June 2023 through 14 June 2023

ER -

Automated Industry Classification of Chinese Enterprises Based on Business Scope Texts Using Deep Learning Methods

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this